FreshContext A context lab · Fife , home
Drawing
02 · Benchmarks
Sheet
2 of 3
Rev
A · 2026-10-01

K2-Horizon-7B · file ← K2-Horizon-7B

BF16

IFM's published full-size file. We made the other two from it, and scored it once. IFM's published GGUF.

Size
18.0 GB
Status
Deleted 10 Sep 2026
Scored runs
2
Smallest Mac
32 GB estimate, 8K context
Results 2 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
nullschema k2-7b-bf16-precision37.5%27.2–49.0Passed 27/72 llama.cpp extraction2026-09-10
worldview k2-7b-bf16-precision30.0%18.1–45.4Passed 12/40 llama.cpp extraction2026-09-10

Runs marked unenforced were measured on a suite that requires constrained decoding, on a server shown not to apply the schema: mlx_lm accepts it and ignores it, and a few other servers and models break it. Those numbers do not measure what the suite is designed to measure. They are kept and labelled rather than deleted.

Corrections 2 to the record published 21 October 2026
  • Build of llama.cpp on 2 runs was 0.4.0-dev (build 10893, commit c32d1dabe), now 0.3.0-dev (build 20, commit 35999d1). Served by the K2 Horizon fork of llama.cpp (build 20, commit 35999d1), not the stock build the stamp named.

    Corrected 26 October 2026 · a mechanical fix

The record How it was made · how it was served · what went wrong · what happened to it

Rebuilt from the lab's records by Claude, an AI model. The results above come straight from the automated runs. How these pages are made.

FileK2-Horizon-7B-BF16.gguf
FormatBF16 GGUF, 18,010,413,440 B (16.77 GiB)
Where fromdownloaded 2026-09-09 ~15:00–15:11Z from IFM/K2-Horizon-7B-GGUF
Statusdeleted 2026-09-10 23:48Z
Hugging Facehttps://huggingface.co/IFM/K2-Horizon-7B-GGUF

Where it came from

  • Repo / file: IFM/K2-Horizon-7B-GGUF / K2-Horizon-7B-BF16.gguf, the only GGUF in the repo on 2026-09-09.
  • Command, with HF_XET_HIGH_PERFORMANCE=1 and mlx-venv/bin/python (the interpreter that had huggingface_hub):
snapshot_download('IFM/K2-Horizon-7B-GGUF', local_dir='models/k2-horizon-7b',
allow_patterns=['*BF16*.gguf','*.json','*.jinja'], max_workers=8)

The first attempt (14:57Z) used hf_hub_download(..., max_workers=8) and died with TypeError:... unexpected keyword argument 'max_workers'. It was switched to snapshot_download so the parallel path applied.

  • Date: 2026-09-09, started 14:59Z, complete by 15:11Z.
  • Who asked: Alan, "the 7b model looks more interesting".

How it was served

labeldates (UTC)binaryctx / -np / KV / -fa / --jinja / --reasoning-formatprofilewhy this label exists
k2-7b-bf16-precision2026-09-10 11:48Z–11:56Zllama.cpp-k2horizon/build/bin/llama-server (fork b20, 35999d1)-c 32768 -np 1 -fa on -ctk q8_0 -ctv q8_0 -ngl 999 --jinja --reasoning-format deepseek, alias k2-7b-bf16extraction (temp 0, seed 42, thinking off)top rung of the same-weights precision ladder

Footprint at load: 16.1 GB RSS. Never seated. Its main use was as the input to the two quants (variant docs K2-Horizon-7B Q8_0 (quantised here from IFM's BF16), K2-Horizon-7B Q4_K_M (quantised here from IFM's BF16)).

Decisions

  • Downloaded only as the quantisation source: "quantise locally rather than convert".
  • Scored once, for the precision question.
  • Deleted 2026-09-10 23:48Z with the 36B and 4B BF16s as "dead weight the precision ladder identified", on Alan's "Yeah". The stated basis was "Q8 ≡ BF16, 0 of 72 cases differ". On this model the two differ by one nullschema case (27 vs 26), and the 0-of-72 identity is the 3.7B's.
  • Not published (IFM's own file).

What went wrong

  • Download failure: hf_hub_download takes no max_workers. Fixed in four minutes.
  • Run-log build stamp: both entries carry llama_build: 0.4.0-dev (build 10893, commit c32d1dabe), the upstream binary. The server was the fork's. runtime_version (b20, 35999d1) is correct.
  • No partial runs and no missing flags. The label's intent (precision only, thinking off) matches --reasoning-format deepseek with the extraction profile.

What happened to it

Downloaded 2026-09-09 → quantised to Q8_0 and Q4_K_M 2026-09-09 → benched 2026-09-10 (2 suites) → deleted 2026-09-10 23:48Z. No RESTORE-deleted-*.sh entry (it predates the RESTORE pattern for this family; the 2026-10-11 tiersAB entry covers only the Q4_K_M folder). Re-downloadable from IFM/K2-Horizon-7B-GGUF (revision not pinned). The run-log rows survive.